Open-Sourcing requirements-skill: Lightweight AI-Assisted Requirements Maintenance Link to heading
I just open-sourced a project I have been using to keep requirements work cleaner in fast, AI-assisted coding cycles:
- Repository: github.com/jt55401/requirements-skill
- Latest release: v0.2.0
The Problem Link to heading
AI-assisted teams can ship quickly, but requirement docs often drift from reality. The common failure modes are predictable:
- broken links between requirements and tickets
- duplicate or overlapping stories
- conflicting acceptance criteria
- weak traceability between requirement intent and actual implementation
Once this drift accumulates, teams lose confidence in requirements as a source of truth.
What requirements-skill Includes Link to heading
The project is intentionally lightweight:
- A structured requirements-as-code layout with single-behavior story files
- Conflict-detection checks for link integrity, duplicate IDs/titles, and overlap signals
- Changelog extraction from conventional commit patterns
- Example SaaS requirements + tickets tree you can adapt
- Agent support for both Claude and Codex/OpenAI workflows
Why This Design Link to heading
I wanted a process that is:
- minimal enough to adopt quickly
- strict enough to catch avoidable documentation drift
- friendly to agentic coding workflows, not in conflict with them
So this is not a heavyweight PM platform replacement. It is a practical kit for teams that want requirement hygiene with very low ceremony.
Licensing And Collaboration Model Link to heading
The project is open for forks and fixes, with explicit attribution and identity boundaries:
GPL-3.0-onlylicense for code collaboration- trademark/naming policy to prevent forks being presented as the official upstream
- clear contribution guidance and funding links
What’s Next Link to heading
I plan to iterate on:
- richer conflict detection heuristics
- easier installation/distribution for the skill files
- tighter commit-to-changelog automation in CI
If you want to contribute improvements, PRs are welcome.
If your team is using AI heavily and requirements drift is already hurting quality, this project should give you a fast baseline to stabilize the process.